Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to regions or regulatory frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mand
    -0.17
    illet
    -0.16
    washer
    -0.15
    æĹħ
    -0.14
    bare
    -0.14
    uctive
    -0.14
    uria
    -0.14
    izz
    -0.14
    ankan
    -0.14
    zac
    -0.14
    POSITIVE LOGITS
    ensburg
    0.21
    isseur
    0.21
    roupe
    0.19
    ierung
    0.19
    iao
    0.18
    ional
    0.18
    gio
    0.18
    ency
    0.17
    lement
    0.17
    tember
    0.17
    Act Density 0.009%

    No Known Activations